Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Adds real context beyond the annotations: partial-update semantics ('Only the values given change'), downstream effect ('every later image use them'), reversibility via undo, and zero point cost. The reversibility framing sits in mild tension with destructiveHint=true, but it clarifies rather than contradicts — the agent learns changes are scoped and undoable.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Four short sentences, front-loaded with what changes, followed by scope, persistence, and undo. No filler or redundancy.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

No output schema exists, yet the description covers scope, persistence, reversibility, and cost — enough for a mutation tool with 10 mostly-enum parameters. It stops short of describing the response or validation/failure behavior (e.g., invalid enum values), a minor gap.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so the baseline is 3, but the description adds the crucial merge semantics — omitted fields are left untouched — which the schema does not state. It also groups the parameters conceptually (roof shape, facade material, etc.), aiding mapping, though it omits 'language' and 'project_id'.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb ('changes the design settings') plus the exact resource and enumerates the affected attributes: roof shape, facade, frames, style, roof covering, storeys, north direction. This distinguishes it cleanly from siblings such as vedutum_set_site_address and vedutum_furnish_rooms.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives clear conditions and an escape hatch ('vedutum_undo_last_change goes back') plus a cost note ('Costs no points'), which helps the agent decide to use it freely. It does not, however, contrast with other design-affecting tools like vedutum_set_site_address or say when-not to use it.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.